© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 5724
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or terms such as "Colle", "Coleonie", and "Gordon"

    oai_token-act-pair · gpt-3.5-turbo

    segments of text related to colleges or educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unbeliev
    -0.63
    pas
    -0.62
    ndra
    -0.62
     Archdemon
    -0.62
     DAC
    -0.60
    drm
    -0.60
    utra
    -0.58
    uggle
    -0.57
     REUTERS
    -0.57
    ierrez
    -0.57
    POSITIVE LOGITS
     Rasm
    0.84
    Ķ
    0.81
    adelphia
    0.76
    rency
    0.76
    aeper
    0.70
    amination
    0.69
    riage
    0.69
    crew
    0.67
    estine
    0.66
    INAL
    0.65
    Activations Density 0.126%

    No Known Activations